{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:25ZODRO4GHKE4GR4NQIT5EZQ7C","short_pith_number":"pith:25ZODRO4","schema_version":"1.0","canonical_sha256":"d772e1c5dc31d44e1a3c6c113e9330f8a71b48284f6b24af1a45d3405d117594","source":{"kind":"arxiv","id":"2607.00672","version":1},"attestation_state":"computed","paper":{"title":"DART: Difficulty-Adaptive Routing for Zero-Shot Video Temporal Grounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mark He Huang, Ming-Hsuan Yang, Zhengbo Zhang, Zhigang Tu","submitted_at":"2026-07-01T09:18:59Z","abstract_excerpt":"Zero-shot video temporal grounding (VTG) localizes events in untrimmed videos from natural language queries without task-specific training. Existing methods rely on frame-query feature matching, which suffices for simple events but struggles with complex multi-stage queries that require understanding temporal ordering and causal structure -- a disparity we call the reasoning gap. We propose DART (Difficulty-Adaptive Routing for Temporal Grounding), which bridges this gap by coupling difficulty-aware routing with structured reasoning in large vision-language models. A query-conditioned Determin"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.00672","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T09:18:59Z","cross_cats_sorted":[],"title_canon_sha256":"ec588f8c5bd3fecc0cd909e87f35ff44bfbd43d6c91f1909596626f6c0b00b8a","abstract_canon_sha256":"17cc8fb600df117daf8e04e907f1758efe7b1bb8052b85639cb617216fd7b876"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:51.024718Z","signature_b64":"rXKaZ1OVL7LYiHpGXWKxZT8saoQcktaFVz2bpcdFMiRhbmhLLo8h/Cja0WRPGppwiIAZEHU6179oeVyrNlZXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d772e1c5dc31d44e1a3c6c113e9330f8a71b48284f6b24af1a45d3405d117594","last_reissued_at":"2026-07-02T01:17:51.024308Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:51.024308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DART: Difficulty-Adaptive Routing for Zero-Shot Video Temporal Grounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mark He Huang, Ming-Hsuan Yang, Zhengbo Zhang, Zhigang Tu","submitted_at":"2026-07-01T09:18:59Z","abstract_excerpt":"Zero-shot video temporal grounding (VTG) localizes events in untrimmed videos from natural language queries without task-specific training. Existing methods rely on frame-query feature matching, which suffices for simple events but struggles with complex multi-stage queries that require understanding temporal ordering and causal structure -- a disparity we call the reasoning gap. We propose DART (Difficulty-Adaptive Routing for Temporal Grounding), which bridges this gap by coupling difficulty-aware routing with structured reasoning in large vision-language models. A query-conditioned Determin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00672","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.00672/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.00672","created_at":"2026-07-02T01:17:51.024375+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00672v1","created_at":"2026-07-02T01:17:51.024375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00672","created_at":"2026-07-02T01:17:51.024375+00:00"},{"alias_kind":"pith_short_12","alias_value":"25ZODRO4GHKE","created_at":"2026-07-02T01:17:51.024375+00:00"},{"alias_kind":"pith_short_16","alias_value":"25ZODRO4GHKE4GR4","created_at":"2026-07-02T01:17:51.024375+00:00"},{"alias_kind":"pith_short_8","alias_value":"25ZODRO4","created_at":"2026-07-02T01:17:51.024375+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/25ZODRO4GHKE4GR4NQIT5EZQ7C","json":"https://pith.science/pith/25ZODRO4GHKE4GR4NQIT5EZQ7C.json","graph_json":"https://pith.science/api/pith-number/25ZODRO4GHKE4GR4NQIT5EZQ7C/graph.json","events_json":"https://pith.science/api/pith-number/25ZODRO4GHKE4GR4NQIT5EZQ7C/events.json","paper":"https://pith.science/paper/25ZODRO4"},"agent_actions":{"view_html":"https://pith.science/pith/25ZODRO4GHKE4GR4NQIT5EZQ7C","download_json":"https://pith.science/pith/25ZODRO4GHKE4GR4NQIT5EZQ7C.json","view_paper":"https://pith.science/paper/25ZODRO4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00672&json=true","fetch_graph":"https://pith.science/api/pith-number/25ZODRO4GHKE4GR4NQIT5EZQ7C/graph.json","fetch_events":"https://pith.science/api/pith-number/25ZODRO4GHKE4GR4NQIT5EZQ7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/25ZODRO4GHKE4GR4NQIT5EZQ7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/25ZODRO4GHKE4GR4NQIT5EZQ7C/action/storage_attestation","attest_author":"https://pith.science/pith/25ZODRO4GHKE4GR4NQIT5EZQ7C/action/author_attestation","sign_citation":"https://pith.science/pith/25ZODRO4GHKE4GR4NQIT5EZQ7C/action/citation_signature","submit_replication":"https://pith.science/pith/25ZODRO4GHKE4GR4NQIT5EZQ7C/action/replication_record"}},"created_at":"2026-07-02T01:17:51.024375+00:00","updated_at":"2026-07-02T01:17:51.024375+00:00"}